Predicting collisions: time-to-contact forecasting based on probabilistic segmentation and system identification

Autor:	Ericka Janet Rechy-Ramirez, Gustavo Quintana-Carapia, Hugues Garnier, Angel Juan Sanchez-Garcia, Antonio Marin-Hernandez, Homero V. Rios-Figueroa
Přispěvatelé:	Electricity, Faculty of Engineering, Universidad Veracruzana, Centre de Recherche en Automatique de Nancy (CRAN), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), Vrije Universiteit Brussel (VUB), Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)
Rok vydání:	2018
Předmět:	0209 industrial biotechnology Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Time to contact 02 engineering and technology computer.software_genre Probabilistic segmentation [SPI.AUTO]Engineering Sciences [physics]/Automatic 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering System identification business.industry Modeling Robotics Computer Science Applications Human-Computer Interaction Robotic systems Hardware and Architecture Control and Systems Engineering Order (business) MAP Key (cryptography) 020201 artificial intelligence & image processing Data mining Artificial intelligence Time-to-contact business computer Software Forecasting
Zdroj:	Advanced Robotics Advanced Robotics, Taylor & Francis, 2018, 32 (8), pp.426-442. ⟨10.1080/01691864.2018.1455604⟩
ISSN:	1568-5535 0169-1864
DOI:	10.1080/01691864.2018.1455604
Popis:	International audience; The Time-to-contact (TTC) estimate is mainly used in robotics navigation, in order to detect potential danger with obstacles in the environment. A key aspect in a robotic system is to perform its tasks promptly. Several approaches have been proposed to estimate reliable TTC in order to avoid collisions in real-time; nevertheless they are time consuming due to a calculation of scene characteristics in every frame. This paper presents an approach to estimate TTC using monocular vision based on the size change of the obstacles over time (); therefore, the robotic system may react promptly to its environment. Our approach collects information from few data of an obstacle, then the behavior of the movement is found through an online recursive modeling process, and finally, a forecasting of the upcoming positions is computed. We segment the obstacles using probabilistic hidden Markov chains. Our proposal is compared to a classical color segmentation approach using two real image sequences, each sequence is composed of 210 frames. Our results show that our proposal obtained smoother segmentations than a traditional color-based approach.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::448e3123bca92090dde93c9410fe7823 https://doi.org/10.1080/01691864.2018.1455604 Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.